java简单web爬虫(网页图片)

java简单web爬虫(网页图片)
效果，执行main（）方法后图片就下载道C盘的res文件夹中。没有的话创建一个文件夹
代码里的常量根据自己的需求修改，代码附到下面。

　

package com.sinitek.sirm.common.utils;

import java.io.*;
import java.net.URL;
import java.net.URLConnection;
import java.util.*;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

/**
 * java简单web爬虫(网页图片)
 */
public class Main {

    // 地址
    private static final String URL = "http://www.xxx";
    // 获取img标签正则
    private static final String IMGURL_REG = "<img.*src=(.*?)[^>]*?>";
    // 获取src路径的正则
    private static final String IMGSRC_REG = "src\\s*=\\s*\"?(.*?)(\"|>|\\s+)";
    //图片原始路径(如果src里的路径正确则不用)
    private static final String IMG_LUJING = "http://xxx/";
    //下载路径
    private static final String LUJING = "C:/res/";


    public static void main(String[] args) {
        try {
            Main cm=new Main();
            //获得html文本内容
            String HTML = cm.getHtml(URL);
            //获取图片标签
            List<String> imgUrl = cm.getImageUrl(HTML);
            //获取图片src地址
            List<String> imgSrc = cm.getImageSrc(imgUrl);
            //下载图片
            cm.Download(imgSrc);

        }catch (Exception e){
            System.out.println("发生错误");
        }

    }


   //获取HTML内容
    private String getHtml(String url)throws Exception{
        URL url1=new URL(url);
        URLConnection connection=url1.openConnection();
        InputStream in=connection.getInputStream();
        InputStreamReader isr=new InputStreamReader(in);
        BufferedReader br=new BufferedReader(isr);

        String line;
        StringBuffer sb=new StringBuffer();
        while((line=br.readLine())!=null){
            sb.append(line,0,line.length());
            sb.append('\n');
        }
        br.close();
        isr.close();
        in.close();
        return sb.toString();
    }

    //获取ImageUrl地址
    private List<String> getImageUrl(String html){
        Matcher matcher=Pattern.compile(IMGURL_REG).matcher(html);
        List<String>listimgurl=new ArrayList<String>();
        while (matcher.find()){
            listimgurl.add(matcher.group());
        }
        return listimgurl;
    }

    //获取ImageSrc地址
    private List<String> getImageSrc(List<String> listimageurl){
        List<String> listImageSrc=new ArrayList<String>();
        for (String image:listimageurl){
            // 匹配<img>中的src数据
            Matcher m = Pattern.compile(IMGSRC_REG).matcher(image);
            while (m.find()) {
                String a = m.group(1);//获取图片路径
                a = IMG_LUJING+a;//数据拼接
                listImageSrc.add(a);
            }
        }
        return listImageSrc;
    }

    //下载图片
    private void Download(List<String> listImgSrc) {
        try {
            //开始时间
            Date begindate = new Date();
            for (String url : listImgSrc) {
                //开始时间
                Date begindate2 = new Date();
                String imageName = url.substring(url.lastIndexOf("/") + 1, url.length());
                URL uri = new URL(url);
                InputStream in = uri.openStream();
                FileOutputStream fo = new FileOutputStream(new File(LUJING+imageName));//路径
                byte[] buf = new byte[1024];
                int length = 0;
                System.out.println("开始下载:" + url);
                while ((length = in.read(buf, 0, buf.length)) != -1) {
                    fo.write(buf, 0, length);
                }
                in.close();
                fo.close();
                System.out.println(imageName + "下载完成");
                //结束时间
                Date overdate2 = new Date();
                double time = overdate2.getTime() - begindate2.getTime();
                System.out.println("耗时：" + time / 1000 + "s");
            }
            Date overdate = new Date();
            double time = overdate.getTime() - begindate.getTime();
            System.out.println("总耗时：" + time / 1000 + "s");
        } catch (Exception e) {
            System.out.println("下载失败");
        }
    }
}